时间序列预测中的数据滑窗操作实例(python实现)

def sliding_window(DataSet, X_width, y_width, gap = 1, multi_vector = None, X_data = True):
    '''
    DataSet has to be as a DataFrame
    '''
    if X_data:
        if multi_vector:
            a,b = DataSet.shape
        else:
            a = DataSet.shape[0]
            b = 1
        c = (a-X_width-y_width-a%gap)/gap
        X = np.reshape(DataSet.iloc[0:X_width,:].values,(1,X_width,b))
        for i in range(len(DataSet) - X_width - y_width):
            i += 1
            if i > c:
                break
            j = i * gap
            tmp = DataSet.iloc[j:j + X_width,:].values
            tmp = np.reshape(tmp,(1,X_width,b))
            X = np.concatenate([X,tmp],0)
        return X
    else:
        if multi_vector:
            print('y_data-error：expect 1D ,given %dD'%DataSet.shape[1])
            return;
        else:
            a = DataSet.shape[0]
        c = (a-X_width-y_width-a%gap)/gap
        y = np.reshape(DataSet.iloc[X_width:X_width + y_width,0].values,(1,y_width))
        for i in range(len(DataSet) - X_width - y_width):
            i += 1
            if i > c:
                break
            j = i * gap + X_width
            tmp = DataSet.iloc[j:j + y_width,:].values
            tmp = np.reshape(tmp,(1,y_width))
            y = np.concatenate([y,tmp])
        return y

#DataSet训练数据集
#X_width使用的历史数据长度
#y_width要预测的数据长度
#X_data是否是X数据集
train_X = sliding_window(DataSet, X_width, y_width)
train_y = sliding_window(DataSet, X_width, y_width, X_data = None)

#DataSet训练数据集
#X_width使用的历史数据长度
#y_width要预测的数据长度
#multi_vector是否为多特征
#X_data是否是X数据集
train_X = sliding_window(DataSet, X_width, y_width, multi_vector = True)
test_y = sliding_window(DataSet, X_width, y_width, multi_vector = True, X_data = None)